Haibo Hu

Authenticating Aggregate Queries over Set-Valued Data with Confidentiality (Extended Abstract)

2018

With recent advances in data-as-a-service (DaaS) and cloud computing, aggregate query services over set-valued data are becoming widely available for business intelligence that drives decision making. However, as the service provider is often a third-party …

Protecting Decision Boundary of Machine Learning Model With Differentially Private Perturbation

2020 · IEEE Transactions on Dependable and Secure Computing

Machine learning service API allows model owners to monetize proprietary models by offering prediction services to third-party users. However, existing literature shows that model parameters are vulnerable to extraction attacks which accumulate prediction queries and …

An extraction attack on image recognition model using VAE-kdtree model

2021

This paper proposes a black box extraction attack model on pre-trained image classifiers to rebuild a functionally equivalent model with high similarity. Common model extraction attacks use a large number of training samples to feed …

DDRM: A Continual Frequency Estimation Mechanism with Local Differential Privacy

2022 · IEEE Transactions on Knowledge and Data Engineering

Many applications rely on continual data collection to provide real-time information services, e.g., real-time road traffic forecasts. However, the collection of original data brings risks to user privacy. Recently, local differential privacy (LDP) has emerged …

Privacy for Free: Leveraging Local Differential Privacy Perturbed Data from Multiple Services

2025 · Proceedings of the VLDB Endowment

Local Differential Privacy (LDP) has emerged as a widely adopted privacy-preserving technique in modern data analytics, enabling users to share statistical insights while maintaining robust privacy guarantees. However, current LDP applications assume a single service …